A human identification system using neural networks demonstrated that analyzing ECG signal subsequences (P, QRS, and T waves) is superior to using the whole period of the ECG signal.
An ECG-based human identification system utilizing specific subsequences (P, QRS, and T waves) and neural networks outperforms methods using the entire ECG period.
A new human identification system based electrocardiogram (ECG) signal is introduced in this work. The human heart is considered to be a unique system of each person. ECG signal therefore represents as an impulse response of the system. The frequency response of the system (Fourier transform of the ECG signal) is employed to be a tool for feature extraction. In addition, the ECG signals employed in this paper, which may be derived from different heart rates from different subjects at the recording time, are normalized to a standard heart rate. Furthermore, not only the whole sequence of 1 period EC signal, containing P, QRS, and T waves, is processed but also its three subsequences, each respectively representing P, QRS, and T waves, is examined. The results of using neural network have demonstrated that subsequences technique is superior to whole period of ECG signal method.
Saechia et al. (2005) studied Human identification. ECG signal subsequences (P, QRS, and T waves) with neural network vs. Whole period of ECG signal method was evaluated on Human identification performance. A human identification system using neural networks demonstrated that analyzing ECG signal subsequences (P, QRS, and T waves) is superior to using the whole period of the ECG signal.